PCA

https://satijalab.org/seurat/articles/pbmc3k_tutorial.html

library(readr)
EZ_Batch1 <- read_csv("EZ_Batch1.csv")

## New names:
## * `` -> ...1

## Rows: 18438 Columns: 31734
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr     (1): ...1
## dbl (31733): EZ.Batch1_HipR-AD-G3-2w_GTACTTTCACATGGGA, EZ.Batch1_HipR-AD-G3-...
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.

EZ_Batch1<-as.data.frame(EZ_Batch1)

head(EZ_Batch1)

library(Seurat)

## Attaching SeuratObject

colnames(EZ_Batch1)[1] <- "gene"
rownames(EZ_Batch1) <- EZ_Batch1$gene
EZ_Batch1$gene <- NULL
head(EZ_Batch1)

library(data.table)


# transpose
tez <- transpose(EZ_Batch1)

# get row and colnames in order
colnames(tez) <- rownames(EZ_Batch1)
rownames(tez) <- colnames(EZ_Batch1)

obj <- CreateSeuratObject(counts=tez, project="EZ_batch1", min.cells = 3, min.features = 200)

## Warning: Feature names cannot have underscores ('_'), replacing with dashes
## ('-')

obj

## An object of class Seurat 
## 31733 features across 12313 samples within 1 assay 
## Active assay: RNA (31733 features, 0 variable features)

obj[["percent.mt"]] <- PercentageFeatureSet(obj, pattern = "^MT-")

VlnPlot(obj, features = c("nFeature_RNA", "nCount_RNA", "percent.mt"), ncol = 3)

## Warning in SingleExIPlot(type = type, data = data[, x, drop = FALSE], idents =
## idents, : All cells have the same value of percent.mt.

plot1 <- FeatureScatter(obj, feature1 = "nCount_RNA", feature2 = "percent.mt")

## Warning in cor(x = data[, 1], y = data[, 2]): the standard deviation is zero

plot2 <- FeatureScatter(obj, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
plot1

plot2

obj <- subset(obj, subset = nFeature_RNA > 200 & nFeature_RNA < 2500 & percent.mt < 5)
obj <- NormalizeData(obj, normalization.method = "LogNormalize", scale.factor = 10000)

obj <- FindVariableFeatures(obj, selection.method = "vst", nfeatures = 2000)

# Identify the 10 most highly variable genes
top10 <- head(VariableFeatures(obj), 10)

# plot variable features with and without labels
plot1 <- VariableFeaturePlot(obj)
plot2 <- LabelPoints(plot = plot1, points = top10, repel = TRUE)

## When using repel, set xnudge and ynudge to 0 for optimal results

plot1

plot2

all.genes <- rownames(obj)
obj <- ScaleData(obj, features = all.genes)

## Centering and scaling data matrix

obj <- RunPCA(obj, features = VariableFeatures(object = obj))

## PC_ 1 
## Positive:  EZ.Batch1-HipR-AD-G1-4w-GACAGAGCATCGGAAG, EZ.Batch1-HipR-AD-G3-2w-GAATGAACACCCATTC, EZ.Batch1-HipR-AD-G1-4w-TAAGCGTCAAGGCTCC, EZ.Batch1-HipR-AD-G1-4w-GCACATAAGCTATGCT, EZ.Batch1-HipR-AD-G1-4w-AAGCCGCTCTCGAGTA, EZ.Batch1-HipR-WT-G3-2w-GAATAAGTCCAAACTG, EZ.Batch1-HipR-WT-G3-2w-GATCGCGCACGGCGTT, EZ.Batch1-HipR-AD-G1-4w-CATCAAGCATCCAACA, EZ.Batch1-HipR-AD-G1-4w-TAGACCATCAAACAAG, EZ.Batch1-HipR-AD-G1-4w-CTGTGCTTCCGAAGAG 
##     EZ.Batch1-HipR-WT-G1-4w-GTCATTTGTATCGCAT, EZ.Batch1-HipR-AD-G3-2w-CACAAACTCATGTCTT, EZ.Batch1-HipR-WT-G3-2w-GCGCAGTGTAAGAGGA, EZ.Batch1-HipR-WT-G3-2w-CGAGAAGCAATGAAAC, EZ.Batch1-HipR-AD-G1-4w-GAGTCCGGTCCATCCT, EZ.Batch1-HipR-AD-G1-4w-TGGCGCACATGTAGTC, EZ.Batch1-HipR-WT-G1-4w-TGCCAAATCAAGATCC, EZ.Batch1-HipR-AD-G1-4w-CTAACTTGTTTGACAC, EZ.Batch1-HipR-AD-G1-4w-ATCATCTTCCTCCTAG, EZ.Batch1-HipR-WT-G1-4w-TCATTACTCAGCGATT 
##     EZ.Batch1-HipR-WT-G3-2w-TACTTGTTCTGCCAGG, EZ.Batch1-HipR-WT-G3-2w-TACGGTACAGGCTCAC, EZ.Batch1-HipR-WT-G3-2w-CCATGTCCAGACAAGC, EZ.Batch1-HipR-AD-G3-2w-AGCCTAAAGAGTTGGC, EZ.Batch1-HipR-AD-G3-2w-TGTTCCGTCGTCACGG, EZ.Batch1-HipR-WT-G3-2w-TGACTAGTCGAACTGT, EZ.Batch1-HipR-WT-G1-4w-CTAAGACCATCGGTTA, EZ.Batch1-HipR-AD-G1-4w-AGCTCTCTCAGTCCCT, EZ.Batch1-HipR-AD-G1-4w-TAGGCATTCCAGATCA, EZ.Batch1-HipR-WT-G3-2w-CTGCCTAAGCCCGAAA 
## Negative:  EZ.Batch1-HipR-AD-G3-2w-TATCTCAAGACTAGGC, EZ.Batch1-HipR-AD-G1-4w-TGAAAGAAGAGACTAT, EZ.Batch1-HipR-WT-G1-4w-GATCAGTGTCCCGACA, EZ.Batch1-HipR-AD-G1-4w-GTGCAGCCACATCCAA, EZ.Batch1-HipR-WT-G3-2w-GTATCTTCACGGTAGA, EZ.Batch1-HipR-AD-G3-2w-CTAGAGTGTTTGTGTG, EZ.Batch1-HipR-AD-G3-2w-CGCCAAGTCAACACGT, EZ.Batch1-HipR-AD-G1-4w-CTTACCGCATGAAGTA, EZ.Batch1-HipR-AD-G1-4w-GTTAAGCCACAGTCGC, EZ.Batch1-HipR-WT-G1-4w-AACACGTCAAGAAAGG 
##     EZ.Batch1-HipR-AD-G3-2w-GATCGATCACAGGAGT, EZ.Batch1-HipR-AD-G3-2w-GCAAACTAGGGAACGG, EZ.Batch1-HipR-WT-G3-2w-CTGCCTATCCTCAATT, EZ.Batch1-HipR-WT-G1-4w-CGTCAGGCATGCAACT, EZ.Batch1-HipR-WT-G1-4w-GGAATAACAACTGGCC, EZ.Batch1-HipR-WT-G1-4w-ATCCGAAGTACACCGC, EZ.Batch1-HipR-AD-G3-2w-CACACCTCACTGTGTA, EZ.Batch1-HipR-WT-G3-2w-CGACCTTTCAGGTTCA, EZ.Batch1-HipR-AD-G3-2w-AAGACCTAGCAGGTCA, EZ.Batch1-HipR-WT-G3-2w-TCAATCTTCACCGGGT 
##     EZ.Batch1-HipR-WT-G3-2w-AGCCTAAAGAGGGATA, EZ.Batch1-HipR-AD-G1-4w-ACGGGCTGTGGTACAG, EZ.Batch1-HipR-WT-G1-4w-TGGCTGGAGGTTCCTA, EZ.Batch1-HipR-WT-G1-4w-GACGTTAAGTCATCCA, EZ.Batch1-HipR-AD-G3-2w-AGCGTATCATAGGATA, EZ.Batch1-HipR-WT-G1-4w-GTCTTCGTCTATCCCG, EZ.Batch1-HipR-WT-G1-4w-CTTAACTTCCCTAACC, EZ.Batch1-HipR-AD-G1-4w-TCAGGTATCGCATGGC, EZ.Batch1-HipR-AD-G1-4w-ATCTACTTCCTGTAGA, EZ.Batch1-HipR-AD-G3-2w-ACGCCAGAGAGCCTAG 
## PC_ 2 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-WT-G3-2w-GCACATATCATAACCG, EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-TACGGATAGTCCGGTC, EZ.Batch1-HipR-WT-G1-4w-AAATGCCAGCTCTCGG, EZ.Batch1-HipR-AD-G1-4w-CACAGTACAGCTGGCT, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-WT-G1-4w-CACAGGCCAGGTCCAC, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-AD-G1-4w-CGTTGGGAGGCAGGTT 
##     EZ.Batch1-HipR-WT-G1-4w-CCAGCGAGTCGGCACT, EZ.Batch1-HipR-AD-G1-4w-ATAGACCTCATGTGGT, EZ.Batch1-HipR-WT-G3-2w-GTCATTTGTTGGTGGA, EZ.Batch1-HipR-AD-G1-4w-CACAGGCGTACGCTGC, EZ.Batch1-HipR-AD-G3-2w-CATTATCAGGATCGCA, EZ.Batch1-HipR-WT-G1-4w-TCATTACGTCAATGTC, EZ.Batch1-HipR-WT-G3-2w-GCTGCAGCAAGCCCAC, EZ.Batch1-HipR-WT-G1-4w-ATGTGTGGTAAACACA, EZ.Batch1-HipR-AD-G1-4w-TTGAACGCAAGGACTG, EZ.Batch1-HipR-AD-G1-4w-CTGGTCTAGACAAAGG 
##     EZ.Batch1-HipR-WT-G1-4w-AGTGGGAAGTTCCACA, EZ.Batch1-HipR-AD-G3-2w-CATCGAAGTCACTGGC, EZ.Batch1-HipR-WT-G3-2w-TCAGCAATCGGCCGAT, EZ.Batch1-HipR-WT-G3-2w-GTCGTAAAGTGGAGTC, EZ.Batch1-HipR-WT-G1-4w-AGAATAGAGCGCCTTG, EZ.Batch1-HipR-WT-G3-2w-CGTCCATGTAGCGCTC, EZ.Batch1-HipR-WT-G3-2w-GCGCAACGTATATGAG, EZ.Batch1-HipR-WT-G3-2w-TGCGTGGTCTTGTACT, EZ.Batch1-HipR-WT-G3-2w-AAATGCCTCACTTACT, EZ.Batch1-HipR-WT-G3-2w-CACCACTTCTTGCCGT 
## Negative:  EZ.Batch1-HipR-WT-G1-4w-CCTAGCTGTGGTCCGT, EZ.Batch1-HipR-WT-G1-4w-GTCACAATCCACGAAT, EZ.Batch1-HipR-AD-G1-4w-TAAGCGTCAAGGCTCC, EZ.Batch1-HipR-AD-G3-2w-CACAAACTCATGTCTT, EZ.Batch1-HipR-AD-G1-4w-TTATGCTAGTACACCT, EZ.Batch1-HipR-WT-G3-2w-TGAAAGATCGATGAGG, EZ.Batch1-HipR-WT-G1-4w-CTCATTATCTTGACGA, EZ.Batch1-HipR-WT-G3-2w-CACACAAGTACCTACA, EZ.Batch1-HipR-WT-G1-4w-TCATTACTCAGCGATT, EZ.Batch1-HipR-AD-G3-2w-ACACTGAAGCTGTTCA 
##     EZ.Batch1-HipR-WT-G3-2w-TTAGGCAAGGGTTCCC, EZ.Batch1-HipR-WT-G1-4w-GAAGCAGCAGTAAGCG, EZ.Batch1-HipR-AD-G1-4w-TGGCGCACAGACGTAG, EZ.Batch1-HipR-WT-G3-2w-CTACCCACAATGTAAG, EZ.Batch1-HipR-AD-G3-2w-ATTACTCTCTGTACGA, EZ.Batch1-HipR-AD-G3-2w-GTTAAGCTCCGCGCAA, EZ.Batch1-HipR-WT-G3-2w-CATCCACCAGACGTAG, EZ.Batch1-HipR-WT-G3-2w-GCCTCTACATGAAGTA, EZ.Batch1-HipR-AD-G3-2w-CTACCCAAGCCCAGCT, EZ.Batch1-HipR-AD-G1-4w-CAGCAGCGTCCTAGCG 
##     EZ.Batch1-HipR-WT-G1-4w-TGAAAGACAAAGAATC, EZ.Batch1-HipR-AD-G1-4w-CGTAGGCTCCAACCAA, EZ.Batch1-HipR-WT-G3-2w-ACGCCAGGTCTGGAGA, EZ.Batch1-HipR-AD-G1-4w-GAGTCCGGTCCATCCT, EZ.Batch1-HipR-WT-G1-4w-GCTGCAGAGGTCGGAT, EZ.Batch1-HipR-WT-G1-4w-TGCCAAATCAAGATCC, EZ.Batch1-HipR-AD-G1-4w-AACTCCCGTCTTCTCG, EZ.Batch1-HipR-AD-G1-4w-GGGAATGAGATCCCAT, EZ.Batch1-HipR-WT-G1-4w-AAACCTGAGCCTTGAT, EZ.Batch1-HipR-AD-G1-4w-ATCTACTGTATTAGCC 
## PC_ 3 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-CGTGTAATCCTGTACC, EZ.Batch1-HipR-AD-G3-2w-GGCTCGACAGATCCAT, EZ.Batch1-HipR-WT-G3-2w-TACGGGCTCTGTCCGT, EZ.Batch1-HipR-WT-G1-4w-CAAGTTGAGGTCGGAT, EZ.Batch1-HipR-WT-G1-4w-GTTAAGCGTGAGGGTT, EZ.Batch1-HipR-AD-G1-4w-AACTTTCCACGGTGTC, EZ.Batch1-HipR-AD-G3-2w-CGTTAGAAGGCATGGT, EZ.Batch1-HipR-AD-G3-2w-GCGCAACTCGAATGGG, EZ.Batch1-HipR-WT-G3-2w-TGGTTCCCACCAGCAC, EZ.Batch1-HipR-AD-G3-2w-AGGTCCGTCCATGCTC 
##     EZ.Batch1-HipR-AD-G3-2w-ACTGCTCCACCAACCG, EZ.Batch1-HipR-AD-G3-2w-TGTATTCCAAACGCGA, EZ.Batch1-HipR-AD-G3-2w-ATGGGAGGTATCTGCA, EZ.Batch1-HipR-WT-G1-4w-AGCTCTCGTTAAGATG, EZ.Batch1-HipR-AD-G1-4w-ATCTACTTCCTGTAGA, EZ.Batch1-HipR-AD-G3-2w-TTGACTTAGTCAAGGC, EZ.Batch1-HipR-WT-G1-4w-TCGTAGAAGATCTGCT, EZ.Batch1-HipR-WT-G1-4w-GGAATAACAACTGGCC, EZ.Batch1-HipR-AD-G1-4w-CCTTCCCCACCGAATT, EZ.Batch1-HipR-AD-G1-4w-AGGCCGTCAATCTACG 
##     EZ.Batch1-HipR-WT-G3-2w-CATCGGGTCAACCATG, EZ.Batch1-HipR-AD-G1-4w-TATCTCACAGCATGAG, EZ.Batch1-HipR-WT-G1-4w-GTCTTCGTCTATCCCG, EZ.Batch1-HipR-WT-G1-4w-TAGTGGTCAGGTGCCT, EZ.Batch1-HipR-WT-G1-4w-CGGGTCATCGGCTACG, EZ.Batch1-HipR-AD-G3-2w-CGGAGTCTCTAGCACA, EZ.Batch1-HipR-AD-G1-4w-CTGCGGAGTGTAATGA, EZ.Batch1-HipR-AD-G3-2w-CCCAGTTTCATGTGGT, EZ.Batch1-HipR-WT-G1-4w-CATCCACTCGTAGATC, EZ.Batch1-HipR-WT-G3-2w-GGCGACTCAGATGAGC 
## Negative:  EZ.Batch1-HipR-WT-G3-2w-ATTCTACCATGAGCGA, EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-AD-G1-4w-CACAGTACAGCTGGCT, EZ.Batch1-HipR-WT-G1-4w-AGCGTCGCATGGTTGT, EZ.Batch1-HipR-WT-G1-4w-GCCAAATCAATGGAGC, EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-AD-G1-4w-TTGAACGCAAGGACTG, EZ.Batch1-HipR-WT-G1-4w-TCATTACGTCAATGTC 
##     EZ.Batch1-HipR-AD-G1-4w-CGTTGGGAGGCAGGTT, EZ.Batch1-HipR-WT-G3-2w-CACCACTTCTTGCCGT, EZ.Batch1-HipR-AD-G3-2w-CATTATCAGGATCGCA, EZ.Batch1-HipR-WT-G1-4w-CACAGGCCAGGTCCAC, EZ.Batch1-HipR-WT-G3-2w-CTCGGGACAGGCAGTA, EZ.Batch1-HipR-WT-G1-4w-AGAATAGAGCGCCTTG, EZ.Batch1-HipR-WT-G3-2w-GTCATTTGTTGGTGGA, EZ.Batch1-HipR-AD-G1-4w-ATAGACCTCATGTGGT, EZ.Batch1-HipR-WT-G1-4w-ATGTGTGGTAAACACA, EZ.Batch1-HipR-WT-G1-4w-AGTGGGAAGTTCCACA 
##     EZ.Batch1-HipR-WT-G3-2w-GCGCAACGTATATGAG, EZ.Batch1-HipR-AD-G3-2w-ATCCACCGTACTCGCG, EZ.Batch1-HipR-WT-G1-4w-CCAGCGAGTCGGCACT, EZ.Batch1-HipR-WT-G3-2w-AAATGCCTCACTTACT, EZ.Batch1-HipR-AD-G3-2w-CATCGAAGTCACTGGC, EZ.Batch1-HipR-WT-G3-2w-GCTGCAGCAAGCCCAC, EZ.Batch1-HipR-WT-G1-4w-AAATGCCAGCTCTCGG, EZ.Batch1-HipR-AD-G3-2w-TTAGGCACATCAGTCA, EZ.Batch1-HipR-AD-G1-4w-CTGGTCTAGACAAAGG, EZ.Batch1-HipR-AD-G1-4w-AGTTGGTCATGGTCTA 
## PC_ 4 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-CACCACTTCTTGCCGT, EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-WT-G1-4w-AGCGTCGCATGGTTGT, EZ.Batch1-HipR-WT-G1-4w-AGAATAGAGCGCCTTG, EZ.Batch1-HipR-WT-G1-4w-AGTGGGAAGTTCCACA, EZ.Batch1-HipR-WT-G3-2w-GCGCAACGTATATGAG, EZ.Batch1-HipR-WT-G1-4w-CACAGGCCAGGTCCAC 
##     EZ.Batch1-HipR-WT-G1-4w-TCATTACGTCAATGTC, EZ.Batch1-HipR-WT-G1-4w-ATGTGTGGTAAACACA, EZ.Batch1-HipR-WT-G3-2w-AAATGCCTCACTTACT, EZ.Batch1-HipR-WT-G3-2w-GTCATTTGTTGGTGGA, EZ.Batch1-HipR-WT-G1-4w-CCAGCGAGTCGGCACT, EZ.Batch1-HipR-AD-G3-2w-ATCCACCGTACTCGCG, EZ.Batch1-HipR-AD-G1-4w-TTGAACGCAAGGACTG, EZ.Batch1-HipR-AD-G3-2w-CATTATCAGGATCGCA, EZ.Batch1-HipR-WT-G1-4w-AAATGCCAGCTCTCGG, EZ.Batch1-HipR-AD-G1-4w-CGTTGGGAGGCAGGTT 
##     EZ.Batch1-HipR-AD-G3-2w-CATCGAAGTCACTGGC, EZ.Batch1-HipR-WT-G1-4w-CTGCTGTGTCGCGGTT, EZ.Batch1-HipR-WT-G3-2w-CTCGGGACAGGCAGTA, EZ.Batch1-HipR-WT-G1-4w-GCCAAATCAATGGAGC, EZ.Batch1-HipR-AD-G1-4w-ATAGACCTCATGTGGT, EZ.Batch1-HipR-AD-G1-4w-CTGGTCTAGACAAAGG, EZ.Batch1-HipR-WT-G3-2w-GCTGCAGCAAGCCCAC, EZ.Batch1-HipR-WT-G3-2w-TCAGCAATCGGCCGAT, EZ.Batch1-HipR-AD-G1-4w-AGTTGGTCATGGTCTA, EZ.Batch1-HipR-WT-G3-2w-CCTAAAGGTACAGTTC 
## Negative:  EZ.Batch1-HipR-WT-G3-2w-GTGCGGTAGTACGTAA, EZ.Batch1-HipR-WT-G3-2w-TTGCGTCTCAGTCAGT, EZ.Batch1-HipR-AD-G1-4w-TGTTCCGCATCACAAC, EZ.Batch1-HipR-WT-G1-4w-TACAGTGCAGCTTAAC, EZ.Batch1-HipR-WT-G3-2w-ATTTCTGAGCCAGGAT, EZ.Batch1-HipR-WT-G3-2w-ACTGATGTCCATTCTA, EZ.Batch1-HipR-WT-G3-2w-GTTCTCGCAGTTCATG, EZ.Batch1-HipR-WT-G3-2w-ATTCTACCATGAGCGA, EZ.Batch1-HipR-WT-G1-4w-TCTCATACACGCATCG, EZ.Batch1-HipR-WT-G1-4w-TAGGCATTCTTCGGTC 
##     EZ.Batch1-HipR-WT-G3-2w-CGTTCTGCAGCTCGCA, EZ.Batch1-HipR-AD-G3-2w-TCGCGTTAGGCGATAC, EZ.Batch1-HipR-WT-G3-2w-GTGCATAGTTAAGGGC, EZ.Batch1-HipR-WT-G3-2w-CCTTCGACACATCCAA, EZ.Batch1-HipR-WT-G3-2w-TACCTATAGCTGTCTA, EZ.Batch1-HipR-WT-G1-4w-ATCGAGTTCTGCGACG, EZ.Batch1-HipR-WT-G3-2w-CTGCCTAAGACAGAGA, EZ.Batch1-HipR-AD-G3-2w-GAACGGATCCGCAGTG, EZ.Batch1-HipR-WT-G1-4w-AACTGGTAGAATCTCC, EZ.Batch1-HipR-WT-G1-4w-TCAGCTCAGTGCAAGC 
##     EZ.Batch1-HipR-AD-G3-2w-TTCCCAGAGGGAGTAA, EZ.Batch1-HipR-WT-G3-2w-ATCCACCGTCTAGTCA, EZ.Batch1-HipR-AD-G1-4w-GTTCATTCATACTACG, EZ.Batch1-HipR-AD-G3-2w-TACGGTATCGATGAGG, EZ.Batch1-HipR-AD-G3-2w-CAGTAACTCCAGTAGT, EZ.Batch1-HipR-WT-G1-4w-AGAATAGAGTGTCCAT, EZ.Batch1-HipR-AD-G3-2w-CTACCCACAAGGCTCC, EZ.Batch1-HipR-AD-G3-2w-GCACTCTGTGTATGGG, EZ.Batch1-HipR-AD-G1-4w-TCGGTAAGTGCGATAG, EZ.Batch1-HipR-WT-G1-4w-ATCACGAAGACACGAC 
## PC_ 5 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-GAGCAGACATCCCATC, EZ.Batch1-HipR-WT-G1-4w-TAGACCACAGTCTTCC, EZ.Batch1-HipR-WT-G1-4w-CGAATGTGTCCGTTAA, EZ.Batch1-HipR-AD-G1-4w-CACAAACTCAGTTAGC, EZ.Batch1-HipR-WT-G3-2w-GGGAATGAGACAGAGA, EZ.Batch1-HipR-AD-G3-2w-TCATTTGAGAAACGAG, EZ.Batch1-HipR-WT-G3-2w-CTCGTACAGCCTATGT, EZ.Batch1-HipR-WT-G3-2w-TGCGCAGTCTGGTATG, EZ.Batch1-HipR-AD-G3-2w-GATTCAGCAACGATGG, EZ.Batch1-HipR-WT-G3-2w-ACCTTTACAAGGACAC 
##     EZ.Batch1-HipR-WT-G1-4w-GAAGCAGCAGCTATTG, EZ.Batch1-HipR-AD-G3-2w-TGAGCATAGGAGTCTG, EZ.Batch1-HipR-WT-G3-2w-CACATTTGTCTGCGGT, EZ.Batch1-HipR-AD-G3-2w-GAATAAGAGGACTGGT, EZ.Batch1-HipR-WT-G1-4w-TATGCCCGTTCTGTTT, EZ.Batch1-HipR-WT-G3-2w-ATCTGCCAGACGCACA, EZ.Batch1-HipR-WT-G3-2w-GAAACTCAGTTCGCGC, EZ.Batch1-HipR-AD-G3-2w-TAGCCGGGTATAAACG, EZ.Batch1-HipR-AD-G3-2w-GGATGTTTCAGCAACT, EZ.Batch1-HipR-AD-G3-2w-TTAGGCACATCAGTCA 
##     EZ.Batch1-HipR-WT-G3-2w-AGAGCTTCAACTGCTA, EZ.Batch1-HipR-AD-G1-4w-GGGACCTGTGGTCTCG, EZ.Batch1-HipR-WT-G3-2w-ACGCCAGCACTCGACG, EZ.Batch1-HipR-WT-G3-2w-CTCGAGGTCCTTGGTC, EZ.Batch1-HipR-WT-G3-2w-CGTAGCGTCTCAAGTG, EZ.Batch1-HipR-AD-G3-2w-TGCGGGTCAGTTCATG, EZ.Batch1-HipR-AD-G1-4w-CCACTACTCGGTGTTA, EZ.Batch1-HipR-WT-G3-2w-ACGGGCTTCCTTTCGG, EZ.Batch1-HipR-WT-G1-4w-ACACCAAGTGTTCGAT, EZ.Batch1-HipR-WT-G3-2w-CCTAGCTGTCAGAATA 
## Negative:  EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-WT-G1-4w-CACAGGCCAGGTCCAC, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-AD-G3-2w-CATTATCAGGATCGCA, EZ.Batch1-HipR-WT-G1-4w-AGTGGGAAGTTCCACA, EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-WT-G3-2w-CACCACTTCTTGCCGT, EZ.Batch1-HipR-WT-G3-2w-GCTGCAGCAAGCCCAC, EZ.Batch1-HipR-WT-G1-4w-AAATGCCAGCTCTCGG 
##     EZ.Batch1-HipR-WT-G3-2w-GCGCAACGTATATGAG, EZ.Batch1-HipR-AD-G3-2w-ATCCACCGTACTCGCG, EZ.Batch1-HipR-WT-G3-2w-TCAGCAATCGGCCGAT, EZ.Batch1-HipR-WT-G1-4w-AGAATAGAGCGCCTTG, EZ.Batch1-HipR-WT-G3-2w-GTCATTTGTTGGTGGA, EZ.Batch1-HipR-WT-G3-2w-CTGATAGCATACTACG, EZ.Batch1-HipR-WT-G3-2w-CCTTCCCGTTCAGACT, EZ.Batch1-HipR-WT-G1-4w-AGCGTCGCATGGTTGT, EZ.Batch1-HipR-AD-G1-4w-CGTTGGGAGGCAGGTT, EZ.Batch1-HipR-WT-G3-2w-CTCGGGACAGGCAGTA 
##     EZ.Batch1-HipR-WT-G1-4w-ATGTGTGGTAAACACA, EZ.Batch1-HipR-WT-G1-4w-CCAGCGAGTCGGCACT, EZ.Batch1-HipR-WT-G3-2w-CCTAAAGGTACAGTTC, EZ.Batch1-HipR-WT-G3-2w-AAATGCCTCACTTACT, EZ.Batch1-HipR-AD-G1-4w-ATAGACCTCATGTGGT, EZ.Batch1-HipR-WT-G1-4w-TCATTACGTCAATGTC, EZ.Batch1-HipR-AD-G3-2w-CATCGAAGTCACTGGC, EZ.Batch1-HipR-AD-G1-4w-TTGAACGCAAGGACTG, EZ.Batch1-HipR-WT-G3-2w-GTCCTCACATAAGACA, EZ.Batch1-HipR-AD-G1-4w-TTAACTCAGAGCCTAG

print(obj[["pca"]], dims = 1:5, nfeatures = 5)

## PC_ 1 
## Positive:  EZ.Batch1-HipR-AD-G1-4w-GACAGAGCATCGGAAG, EZ.Batch1-HipR-AD-G3-2w-GAATGAACACCCATTC, EZ.Batch1-HipR-AD-G1-4w-TAAGCGTCAAGGCTCC, EZ.Batch1-HipR-AD-G1-4w-GCACATAAGCTATGCT, EZ.Batch1-HipR-AD-G1-4w-AAGCCGCTCTCGAGTA 
## Negative:  EZ.Batch1-HipR-AD-G3-2w-TATCTCAAGACTAGGC, EZ.Batch1-HipR-AD-G1-4w-TGAAAGAAGAGACTAT, EZ.Batch1-HipR-WT-G1-4w-GATCAGTGTCCCGACA, EZ.Batch1-HipR-AD-G1-4w-GTGCAGCCACATCCAA, EZ.Batch1-HipR-WT-G3-2w-GTATCTTCACGGTAGA 
## PC_ 2 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-WT-G3-2w-GCACATATCATAACCG, EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-TACGGATAGTCCGGTC, EZ.Batch1-HipR-WT-G1-4w-AAATGCCAGCTCTCGG 
## Negative:  EZ.Batch1-HipR-WT-G1-4w-CCTAGCTGTGGTCCGT, EZ.Batch1-HipR-WT-G1-4w-GTCACAATCCACGAAT, EZ.Batch1-HipR-AD-G1-4w-TAAGCGTCAAGGCTCC, EZ.Batch1-HipR-AD-G3-2w-CACAAACTCATGTCTT, EZ.Batch1-HipR-AD-G1-4w-TTATGCTAGTACACCT 
## PC_ 3 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-CGTGTAATCCTGTACC, EZ.Batch1-HipR-AD-G3-2w-GGCTCGACAGATCCAT, EZ.Batch1-HipR-WT-G3-2w-TACGGGCTCTGTCCGT, EZ.Batch1-HipR-WT-G1-4w-CAAGTTGAGGTCGGAT, EZ.Batch1-HipR-WT-G1-4w-GTTAAGCGTGAGGGTT 
## Negative:  EZ.Batch1-HipR-WT-G3-2w-ATTCTACCATGAGCGA, EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-AD-G1-4w-CACAGTACAGCTGGCT 
## PC_ 4 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-CACCACTTCTTGCCGT, EZ.Batch1-HipR-AD-G3-2w-AACGTTGTCTGGAGCC, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA 
## Negative:  EZ.Batch1-HipR-WT-G3-2w-GTGCGGTAGTACGTAA, EZ.Batch1-HipR-WT-G3-2w-TTGCGTCTCAGTCAGT, EZ.Batch1-HipR-AD-G1-4w-TGTTCCGCATCACAAC, EZ.Batch1-HipR-WT-G1-4w-TACAGTGCAGCTTAAC, EZ.Batch1-HipR-WT-G3-2w-ATTTCTGAGCCAGGAT 
## PC_ 5 
## Positive:  EZ.Batch1-HipR-AD-G3-2w-GAGCAGACATCCCATC, EZ.Batch1-HipR-WT-G1-4w-TAGACCACAGTCTTCC, EZ.Batch1-HipR-WT-G1-4w-CGAATGTGTCCGTTAA, EZ.Batch1-HipR-AD-G1-4w-CACAAACTCAGTTAGC, EZ.Batch1-HipR-WT-G3-2w-GGGAATGAGACAGAGA 
## Negative:  EZ.Batch1-HipR-AD-G3-2w-ATCTGCCAGCCAACAG, EZ.Batch1-HipR-WT-G3-2w-TCATTACTCTTCGAGA, EZ.Batch1-HipR-WT-G1-4w-CACAGGCCAGGTCCAC, EZ.Batch1-HipR-AD-G3-2w-CCAGCGACAGTTCCCT, EZ.Batch1-HipR-AD-G3-2w-CATTATCAGGATCGCA

DimPlot(obj, reduction = "pca")

DimHeatmap(obj, dims = 1, cells = 500, balanced = TRUE)

ElbowPlot(obj)

obj <- FindNeighbors(obj, dims = 1:10)

## Computing nearest neighbor graph

## Computing SNN

obj <- FindClusters(obj, resolution = 0.5)

## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 9013
## Number of edges: 255742
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.8024
## Number of communities: 11
## Elapsed time: 2 seconds

head(Idents(obj), 5)

##        Mrpl15         Tcea1 4732440D04Rik       Gm26901          Rrs1 
##             0             0             2             2             5 
## Levels: 0 1 2 3 4 5 6 7 8 9 10

obj <- RunUMAP(obj, dims = 1:20)

## Warning: The default method for RunUMAP has changed from calling Python UMAP via reticulate to the R-native UWOT using the cosine metric
## To use Python UMAP via reticulate, set umap.method to 'umap-learn' and metric to 'correlation'
## This message will be shown once per session

## 01:27:36 UMAP embedding parameters a = 0.9922 b = 1.112

## 01:27:36 Read 9013 rows and found 20 numeric columns

## 01:27:36 Using Annoy for neighbor search, n_neighbors = 30

## 01:27:36 Building Annoy index with metric = cosine, n_trees = 50

## 0%   10   20   30   40   50   60   70   80   90   100%

## [----|----|----|----|----|----|----|----|----|----|

## **************************************************|
## 01:27:38 Writing NN index file to temp file D:\Users\YH881\AppData\Local\Temp\91\RtmpwjU9fb\file356c42ad9618d
## 01:27:38 Searching Annoy index using 1 thread, search_k = 3000
## 01:27:43 Annoy recall = 100%
## 01:27:44 Commencing smooth kNN distance calibration using 1 thread
## 01:27:45 Initializing from normalized Laplacian + noise
## 01:27:45 Commencing optimization for 500 epochs, with 419304 positive edges
## 01:28:25 Optimization finished

DimPlot(obj, reduction = "umap")

saveRDS(obj, file = "ez1.rds")

# find all markers of cluster 2

cluster2.markers <- FindMarkers(obj, ident.1 = 2, min.pct = 0.15)

## For a more efficient implementation of the Wilcoxon Rank Sum Test,
## (default method for FindMarkers) please install the limma package
## --------------------------------------------
## install.packages('BiocManager')
## BiocManager::install('limma')
## --------------------------------------------
## After installation of limma, Seurat will automatically use the more 
## efficient implementation (no further action necessary).
## This message will be shown once per session

head(cluster2.markers, n = 5)